New thesis on improving early detection of cancer
Hi Elinor Nemlander, doctoral student at the Division of Family Medicine and Primary Care. On January 31 you will defend your thesis ”Early cancer detection through symptoms and signs”. What is the main focus of the thesis?
”My thesis focuses on improving early cancer detection by analysing symptoms and clinical signs using innovative methods, such as machine learning. The studies explore how data from primary and specialised care can be utilised to develop tools that support general practitioners in identifying patients at high risk of cancer,” says Elinor Nemlander, doctoral student at the Department of Neurobiology, Care Sciences and Society.
Which are the most important results?
”The most important results show that machine learning models can predict lung cancer based on symptom questionnaires and colorectal cancer using coded diagnostic data and symptom codes. Additionally, the analyses reveal that newly developed anaemia is strongly associated with an increased risk of cancer and mortality within 18 months, making it an important early warning signal in primary care.”
How can this new knowledge contribute to the improvement of people’s health?
”The findings from this thesis can support the development of clinical risk assessment tools to identify high-risk cancer patients earlier, leading to faster investigations and improved treatment outcomes. By leveraging machine learning and existing healthcare data, these tools can make healthcare more efficient and reduce unnecessary examinations, benefiting both patients and the healthcare system.”
What’s in the future for you? Will you continue to conduct research?
”I plan to continue researching early cancer diagnostics and to build upon the results of my thesis. My goal is to develop new tools that can be integrated into existing systems in primary care. In the future, I hope such tools can reduce diagnostic delays, improve patient outcomes, and optimise healthcare resource allocation.”